
import os
import sys
from random import randint
import urllib
import numpy as np
import pandas as pd
from pathlib import Path
import plotly.express as px
import matplotlib.pyplot as plt


path = 'data/real_estate_data.csv'
url = 'https://code.s3.yandex.net/datasets/real_estate_data.csv'
Path('data').mkdir(parents=True, exist_ok=True)
if not os.path.exists(path):
    print(f'real_estate_data.csv не найден. Будет загружен из сети.')
    _ = urllib.request.urlretrieve(url, path)
base = pd.read_csv('data/real_estate_data.csv', sep='\t')


# pd.options.mode.chained_assignment = None


data = pd.DataFrame(base)
data.info()
print(data.shape)

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 23699 entries, 0 to 23698
Data columns (total 22 columns):
 #   Column                Non-Null Count  Dtype  
---  ------                --------------  -----  
 0   total_images          23699 non-null  int64  
 1   last_price            23699 non-null  float64
 2   total_area            23699 non-null  float64
 3   first_day_exposition  23699 non-null  object 
 4   rooms                 23699 non-null  int64  
 5   ceiling_height        14504 non-null  float64
 6   floors_total          23613 non-null  float64
 7   living_area           21796 non-null  float64
 8   floor                 23699 non-null  int64  
 9   is_apartment          2775 non-null   object 
 10  studio                23699 non-null  bool   
 11  open_plan             23699 non-null  bool   
 12  kitchen_area          21421 non-null  float64
 13  balcony               12180 non-null  float64
 14  locality_name         23650 non-null  object 
 15  airports_nearest      18157 non-null  float64
 16  cityCenters_nearest   18180 non-null  float64
 17  parks_around3000      18181 non-null  float64
 18  parks_nearest         8079 non-null   float64
 19  ponds_around3000      18181 non-null  float64
 20  ponds_nearest         9110 non-null   float64
 21  days_exposition       20518 non-null  float64
dtypes: bool(2), float64(14), int64(3), object(3)
memory usage: 3.7+ MB
(23699, 22)


display(data.head(3))
display(data.describe().T)


def get_empty_cols(data):
    '''Создание кортежа с столбцами, в которых присутствуют пропущенные значения'''
    cols_had_null = {col: round(data[col].isna().sum() / data.shape[0], 3) for col in data.columns}
    return {k: v for k, v in cols_had_null.items() if v}

def print_na_info(data):
    print("\n".join(["{:<25}{:<10.1%}".format(k, v) for k, v in get_empty_cols(data).items()]))


print_na_info(data)

ceiling_height           38.8%     
floors_total             0.4%      
living_area              8.0%      
is_apartment             88.3%     
kitchen_area             9.6%      
balcony                  48.6%     
locality_name            0.2%      
airports_nearest         23.4%     
cityCenters_nearest      23.3%     
parks_around3000         23.3%     
parks_nearest            65.9%     
ponds_around3000         23.3%     
ponds_nearest            61.6%     
days_exposition          13.4%


data = data[~data['locality_name'].isna()]


def parse_locality(row):
    i = 0
    while i < len(row):
        if row[i].isupper():
            break
        i += 1
    return row[i:].lower().replace('ё', 'e').capitalize()

data.loc[:, 'locality_name'] = data.locality_name.apply(parse_locality)


locality_name_freq = data.locality_name.value_counts().to_frame()
pd.concat([locality_name_freq.head(), locality_name_freq.tail()])


data.is_apartment = data.apply(lambda x: True if x['rooms'] > 1 and x['studio'] is False else False , axis=1)
"{:.1%}".format(data.is_apartment.isna().sum() / data.shape[0] * 100)

'0.0%'


def insert_by_locality(data, col, fill_by_med=True):
    medians = data.groupby('locality_name')[col].median().dropna()
    for index, value in zip(medians.index, medians):
        data.loc[(data[col].isna()) & (data['locality_name'] == index), col] = value
    print('{:20} is filled by median of locality data'.format(col), end=' ')
    if data[col].isna().sum() and fill_by_med:
        data.loc[:, col] = data.fillna(data[col].median())
        print('& been filled by median of col')
    else:
        print()
    return data

def apply_insert_by_locality_for_cols(data, cols, fill_by_med=True):
    for col in cols:
        data = insert_by_locality(data, col, fill_by_med=fill_by_med) 
    return data


first_part = 'ceiling_height', 'floors_total', 'living_area', 'kitchen_area', 'balcony', 'days_exposition'
second_part = 'airports_nearest', 'cityCenters_nearest', 'parks_around3000', 'parks_nearest',\
                    'ponds_around3000', 'ponds_nearest' 

data = apply_insert_by_locality_for_cols(data, first_part)
data = apply_insert_by_locality_for_cols(data, second_part, fill_by_med=False)
print("#" * 100)
print_na_info(data)

ceiling_height       is filled by median of locality data & been filled by median of col
floors_total         is filled by median of locality data 
living_area          is filled by median of locality data & been filled by median of col
kitchen_area         is filled by median of locality data & been filled by median of col
balcony              is filled by median of locality data & been filled by median of col
days_exposition      is filled by median of locality data & been filled by median of col
airports_nearest     is filled by median of locality data 
cityCenters_nearest  is filled by median of locality data 
parks_around3000     is filled by median of locality data 
parks_nearest        is filled by median of locality data 
ponds_around3000     is filled by median of locality data 
ponds_nearest        is filled by median of locality data 
####################################################################################################
airports_nearest         20.4%     
cityCenters_nearest      20.4%     
parks_around3000         20.4%     
parks_nearest            25.4%     
ponds_around3000         20.4%     
ponds_nearest            20.9%


def parse_two_cols(data, f, s):
    '''
        Нахождение данных в столбце s для столбца f DataFrame data
        Заполнение спец значением -1 и перевод к т д int
    '''
    def appl(row):
        if row[s] > 0 and f != 'cityCenters_nearest':
            return 3000
        else:
            return row[f]
        
    is_check = data[f].isna().sum() == ((data[f].isna()) & (data[s].isna())).sum()
    data[s] = data[s].fillna(-1.0).astype(int)    
    if is_check:
        print(f'There\'s no reason to search info in {s} for {f}')
    else:
        print(f'Search info in {s} for {f}')
        data[f] = data.apply(appl, axis=1)

    data[f] = data[f].fillna(-1.0).astype(int)

    if s != 'airports_nearest':
        data = data.drop(s, axis=1)
    return data

cols_parse = ('parks_around3000', 'parks_nearest'), ('ponds_around3000', 'ponds_nearest'),\
                ('airports_nearest', 'cityCenters_nearest')
cols_parse = tuple([item[::-1] for item in cols_parse])

for cols in cols_parse:
    data = parse_two_cols(data, *cols)

Search info in parks_around3000 for parks_nearest
Search info in ponds_around3000 for ponds_nearest
There's no reason to search info in airports_nearest for cityCenters_nearest


cols_parse = 'airports_nearest', 'cityCenters_nearest', 'parks_nearest', 'ponds_nearest'
data.loc[:, cols_parse].describe().T


for col in ['parks_nearest', 'ponds_nearest']:
    data[col] = data[col].astype(np.uint16)


data["floors_total"] = data.floors_total.astype(np.uint8)
data["balcony"] = data.balcony.astype(np.uint8)
data['days_exposition'] = data.days_exposition.astype(np.uint32)
data['last_price'] = data.last_price.astype(np.uint32)


data.columns = [
    'total_images', 'price', 'total_area', 'first_day_exp',
    'rooms', 'ceiling_height', 'floors_total', 'living_area', 'floor',
    'apartment', 'studio', 'open_plan', 'kitchen_area', 'balcony',
    'location', 'air_nearest', 'city_nearest',
    'parks_nearest', 'ponds_nearest', 'days_exp'
]


def describe_enhanced(data, list_cols):
    '''
        Расширение базового метода `describe` нижниму и верхними оценками границ
        выбросов в данных (интерквартильный размах и 3 сигмы)
    '''
    descr = data[list_cols].describe().T
    descr["low_std"] = descr["mean"] - descr["std"] * 3
    descr["low_iqr"] = descr["25%"] - (descr["75%"] - descr["25%"]) * 1.5
    descr["up_iqr"] = descr["75%"] + (descr["75%"] - descr["25%"]) * 1.5
    descr["up_std"] = descr["mean"] + descr["std"] * 3
    if isinstance(descr, pd.Series):
        return descr.to_frame().T
    return descr

def del_anomal_values(data, info_descr, list_cols):
    for col in list_cols:
        low, up = info_descr.loc[col, 'low_iqr'], info_descr.loc[col, 'up_iqr'] 
        data = data[(low < data[col]) & (data[col] < up)]
    return data


col_info = ['kitchen_area', 'living_area', 'total_area'], ['Площадь кухни', 'Жилая площадь', 'Общая площадь'] 

areas_info = describe_enhanced(data, col_info[0])
display(areas_info)

fig = px.histogram(data, x=col_info[0],
                     barmode="overlay",
                     marginal="box",
                     range_x=(areas_info["min"].min(), areas_info["up_std"].max()),
                     title="Распределения " + ", ".join(map(lambda l: f"`{l}`", col_info[1])),
) 
fig.update_layout(
    xaxis_title='Площадь (кв м)',
    yaxis_title='Кол-во'
)


data = del_anomal_values(data, areas_info, col_info[0])


data.loc[:, 'price_m'] = data.price.apply(lambda x: x / 10 ** 6).astype(np.uint8)


col_info = 'price_m', 'Цена на момент снятия объявления, млн руб'

info = describe_enhanced(data, col_info[0])
display(info)

fig = px.histogram(data[col_info[0]],
                   barmode="overlay",
                   marginal="box",
                   title=col_info[1],
)
fig.update_layout(
    xaxis_title=col_info[1],
    yaxis_title="Кол-во"
)


data = del_anomal_values(data, info, [col_info[0]])


col_info = 'rooms', 'Количество комнат'

info = describe_enhanced(data, col_info[0])
display(info)

fig = px.histogram(data[col_info[0]],
                   barmode="overlay",
                   marginal="box",
                   title=col_info[1],
                   nbins=30
)
fig.update_layout(
    xaxis_title=col_info[1],
    yaxis_title="Кол-во"
)


col_info = 'ceiling_height', 'Высота потолков (м)'

info = describe_enhanced(data, col_info[0])
display(info)

fig = px.histogram(data[col_info[0]],
                   barmode="overlay",
                   marginal="box",
                   title=col_info[1],
)
fig.update_layout(
    xaxis_title=col_info[1],
    yaxis_title="Кол-во"
)


data = del_anomal_values(data, info, [col_info[0]])


info = describe_enhanced(data, col_info[0])
display(info)
fig = px.histogram(data[col_info[0]],
                   barmode="overlay",
                   marginal="box",
                   title=col_info[1],
                   nbins=50
)
fig.update_layout(
    xaxis_title=col_info[1],
    yaxis_title="Кол-во"
)


data.loc[:, 'price_sq_m'] = (data['price'] / data['total_area'])


data.loc[:, 'date_exp'] = pd.to_datetime(data['first_day_exp'])

data.loc[:, 'day_exp'] = data['date_exp'].dt.day
data.loc[:, 'month_exp'] = data['date_exp'].dt.month
data.loc[:, 'year_exp'] = data['date_exp'].dt.year

data = data.drop('first_day_exp', axis=1)


def apl_floor(row):
    if row.floor == row.floors_total:
        return 'Последний'
    if row.floor == 1:
        return 'Первый'
    return 'Другой'

data.loc[:, 'floor'] = data.apply(apl_floor, axis=1)
data = data.drop('floors_total', axis=1)


data.loc[:, 'living_total'] = round(data.living_area / data.total_area, 3)
data.loc[:, 'kitchen_total'] = round(data.kitchen_area / data.total_area, 3)


data.loc[:, 'city_nearest_km'] = (data.city_nearest // 1000).astype(np.uint8)


for col in ['total_images', 'rooms', 'ceiling_height', 'balcony', 'days_exp',\
            'day_exp', 'month_exp', 'year_exp', 'city_nearest_km']:
    data.loc[:, col] =  data.loc[:, col].astype(np.uint16)

/var/folders/ks/pthjmky532s9spw_v5gndt6wb6v_26/T/ipykernel_72557/2396148798.py:3: FutureWarning:

In a future version, `df.iloc[:, i] = newvals` will attempt to set the values inplace instead of always setting a new array. To retain the old behavior, use either `df[df.columns[i]] = newvals` or, if columns are non-unique, `df.isetitem(i, newvals)`

4. Исследовательский анализ данных ¶


col_info = ['kitchen_total', 'living_total'], ['Пл-дь кухни к общей', 'Жилая пл-дь к общей']

info = describe_enhanced(data, col_info[0])
display(info)

fig = px.histogram(data, x=col_info[0],
                     barmode="overlay",
                     marginal="box",
                     range_x=(info["min"].min(), info["up_std"].max()),
                     title="Распределения " + ", ".join(map(lambda l: f"`{l}`", col_info[1])),
) 
fig.update_layout(
    xaxis_title='Значения отношений соответствующих площадей',
    yaxis_title='Кол-во'
)


data = del_anomal_values(data, info, col_info[0])


col_info = "days_exp", "Время продажи квартиры"


info = describe_enhanced(data, col_info[0])
display(info)
fig = px.histogram(data[col_info[0]],
                   barmode="overlay",
                   marginal="box",
                   title=col_info[1],
                   nbins=50
)
fig.update_layout(
    xaxis_title=col_info[1],
    yaxis_title="Кол-во"
)


data = del_anomal_values(data, info, [col_info[0]])


col_parse = 'price_sq_m'
cols_parse = ['total_area', 'rooms', 'floor', 'city_nearest_km']

fig, axises = plt.subplots(1, len(cols_parse))  

for col, axis in zip(cols_parse, axises):
    if col != 'floor':
        correlation = round(data[col_parse].corr(data[col]), 2)
        print('{} ~ {: ^13} ->{: ^10}'.format(col_parse, col, correlation))  
    if col == 'floor':
        (data
            .groupby(col)[col_parse].median().reset_index()
            .plot(kind='bar', x='floor', y=col_parse, label=col, legend=True, grid=True, figsize=(17, 7), ax=axis)
        )
    elif col == 'rooms':
        (data
            .groupby(col)[col_parse].median().reset_index(drop=True)
            .plot(label=col, legend=True, grid=True, figsize=(17, 7), ax=axis)
        )
    else:
        (data
            .groupby(col)[col_parse].median().reset_index()
            .plot(kind='scatter', x=col, y=col_parse, label=col,\
                  legend=True, grid=True, alpha=0.5, figsize=(17, 7), ax=axis)
        )
   
        plt.xlabel(col)
plt.show()

price_sq_m ~  total_area   ->  -0.12   
price_sq_m ~     rooms     ->  -0.26   
price_sq_m ~ city_nearest_km ->  -0.65


data_corr = data.corr()
data_corr_trunc = pd.DataFrame(np.tril(data_corr, k=-1),
                               columns=data_corr.columns,
                               index=data_corr.index
)
px.imshow(data_corr_trunc.replace({0: None}),
          text_auto=".1f",
          zmin=-1,
          zmax=1,
          width=700,
          height=700
)

/var/folders/ks/pthjmky532s9spw_v5gndt6wb6v_26/T/ipykernel_72557/1713752210.py:1: FutureWarning:

The default value of numeric_only in DataFrame.corr is deprecated. In a future version, it will default to False. Select only valid columns or specify the value of numeric_only to silence this warning.


col_parse = 'price_sq_m'
cols_parse = ['day_exp', 'month_exp', 'year_exp']

data_corr = data[cols_parse + [col_parse]].corr()
data_corr_trunc = pd.DataFrame(np.tril(data_corr, k=-1),
                               index=data_corr.index,
                               columns=data_corr.columns)
fig = px.imshow(data_corr_trunc.replace({0: None}),
          zmin=-1, zmax=1, text_auto=".1f")
fig.show()

px.line(data.groupby(col)[cols_parse].median(), log_y=True).show()


fig = px.line(data.groupby('city_nearest_km').agg(
    price_sq_m_median=("price_sq_m", np.median),
    price_sq_m_mean=("price_sq_m", np.mean),
))
fig.update_layout(
    title="Title",
    xaxis_title="x",
    yaxis_title="y",
)


data_top_10_count = (data
    .groupby('location').agg({'rooms':'count', 'price_sq_m':'mean'}).reset_index()
    .sort_values(by='rooms', ascending=False).reset_index(drop=True)
)
data_top_10_count.loc[:, 'price_sq_m'] = data_top_10_count['price_sq_m'].astype(int)
data_top_10_count.columns = ['location', 'count', 'price_sq_m']

print('{:#^70}'.format('Первые 10 нас. пунктов по количеству объявлений'))
display(data_top_10_count.head(10))

###########Первые 10 нас. пунктов по количеству объявлений############

/var/folders/ks/pthjmky532s9spw_v5gndt6wb6v_26/T/ipykernel_72557/1076292836.py:5: FutureWarning:

In a future version, `df.iloc[:, i] = newvals` will attempt to set the values inplace instead of always setting a new array. To retain the old behavior, use either `df[df.columns[i]] = newvals` or, if columns are non-unique, `df.isetitem(i, newvals)`


data_top_price = (data
#                     .groupby('location')['price_sq_m'].mean().reset_index()
            .groupby('location').agg({'rooms':'count', 'price_sq_m':'mean'}).reset_index()
            .sort_values(by='price_sq_m', ascending=False)
)
data_top_price.loc[:, 'price_sq_m'] = data_top_price['price_sq_m'].astype(int)
data_top_price.columns = ['location', 'count', 'price_sq_m']

display('{:#^70}'.format('Топ по цене (первые 10)'))
display(data_top_price.head(10).reset_index(drop=True))
display('{:#^70}'.format('Топ по цене (последние 10)'))
display(data_top_price.tail(10).reset_index(drop=True))

/var/folders/ks/pthjmky532s9spw_v5gndt6wb6v_26/T/ipykernel_72557/965368589.py:6: FutureWarning:

In a future version, `df.iloc[:, i] = newvals` will attempt to set the values inplace instead of always setting a new array. To retain the old behavior, use either `df[df.columns[i]] = newvals` or, if columns are non-unique, `df.isetitem(i, newvals)`

'#######################Топ по цене (первые 10)########################'

'######################Топ по цене (последние 10)######################'


city_nearest_info = describe_enhanced(data, ['city_nearest_km'])
city_nearest_info.T


ax = (data
    .query('location == "Санкт-Петербург"')
    .groupby('city_nearest_km')['price_sq_m'].mean()
    .plot(label='Цена кв метра в Петербурге', figsize=(15, 7), grid=True, legend=True)
)

plt.xlabel('Удалённость от центра Петербурга')
plt.ylabel('Цена кв метра недвижимости')
plt.show()


border_center = 7


# cc - city_center
list_cols = 'location', 'total_area', 'price_m', 'rooms', 'ceiling_height', 'price_sq_m', 'city_nearest_km', 'floor',\
                'day_exp', 'month_exp', 'year_exp'
data_cc = data.query('0 <= city_nearest_km <= @border_center').loc[:, list_cols]
data_cc.describe().T


col_parse = 'price_sq_m'
cols_parse = ['total_area', 'rooms', 'floor', 'city_nearest_km']

fig, axises = plt.subplots(1, len(cols_parse))  

for col, axis in zip(cols_parse, axises):
    if col != 'floor':
        correlation = round(data_cc[col_parse].corr(data_cc[col]), 2)
        print('{} ~ {: ^13} ->{: ^10}'.format(col_parse, col, correlation))  
    if col == 'floor':
        (data_cc
            .groupby(col)[col_parse].median().reset_index()
            .plot(kind='bar', x='floor', y=col_parse, label=col, legend=True, grid=True, figsize=(17, 7), ax=axis)
        )
    elif col == 'rooms':
        (data_cc
            .groupby(col)[col_parse].median().reset_index(drop=True)
            .plot(label=col, legend=True, grid=True, figsize=(17, 7), ax=axis)
        )
    else:
        (data_cc
            .groupby(col)[col_parse].median().reset_index()
            .plot(kind='scatter', x=col, y=col_parse, label=col,\
                  legend=True, grid=True, alpha=0.7, figsize=(17, 7), ax=axis)
        )
   
        plt.xlabel(col)
plt.show()

price_sq_m ~  total_area   ->  -0.46   
price_sq_m ~     rooms     ->  -0.52   
price_sq_m ~ city_nearest_km ->   0.04


col_parse = 'price_sq_m'
cols_parse = ['day_exp', 'month_exp', 'year_exp']

fig, axises = plt.subplots(1, len(cols_parse))

for col, axis in zip(cols_parse, axises):
    correlation = round(data_cc[col_parse].corr(data_cc[col]), 2)
    print('{} ~ {: ^13} ->{: ^10}'.format(col_parse, col, correlation))
        
    (data_cc
        .groupby(col)[col_parse].median()
        .plot(label='Цена кв метра', legend=True, grid=True, figsize=(17, 7), ax=axis)
    )
plt.show()

price_sq_m ~    day_exp    ->   0.03   
price_sq_m ~   month_exp   ->  -0.05   
price_sq_m ~   year_exp    ->   0.18

	total_images	last_price	total_area	first_day_exposition	rooms	ceiling_height	floors_total	living_area	floor	is_apartment	...	kitchen_area	balcony	locality_name	airports_nearest	cityCenters_nearest	parks_around3000	parks_nearest	ponds_around3000	ponds_nearest	days_exposition
0	20	13000000.0	108.0	2019-03-07T00:00:00	3	2.7	16.0	51.0	8	NaN	...	25.0	NaN	Санкт-Петербург	18863.0	16028.0	1.0	482.0	2.0	755.0	NaN
1	7	3350000.0	40.4	2018-12-04T00:00:00	1	NaN	11.0	18.6	1	NaN	...	11.0	2.0	посёлок Шушары	12817.0	18603.0	0.0	NaN	0.0	NaN	81.0
2	10	5196000.0	56.0	2015-08-20T00:00:00	2	NaN	5.0	34.3	4	NaN	...	8.3	0.0	Санкт-Петербург	21741.0	13933.0	1.0	90.0	2.0	574.0	558.0

	count	mean	std	min	25%	50%	75%	max
total_images	23699.0	9.858475e+00	5.682529e+00	0.0	6.00	9.00	14.0	50.0
last_price	23699.0	6.541549e+06	1.088701e+07	12190.0	3400000.00	4650000.00	6800000.0	763000000.0
total_area	23699.0	6.034865e+01	3.565408e+01	12.0	40.00	52.00	69.9	900.0
rooms	23699.0	2.070636e+00	1.078405e+00	0.0	1.00	2.00	3.0	19.0
ceiling_height	14504.0	2.771499e+00	1.261056e+00	1.0	2.52	2.65	2.8	100.0
floors_total	23613.0	1.067382e+01	6.597173e+00	1.0	5.00	9.00	16.0	60.0
living_area	21796.0	3.445785e+01	2.203045e+01	2.0	18.60	30.00	42.3	409.7
floor	23699.0	5.892358e+00	4.885249e+00	1.0	2.00	4.00	8.0	33.0
kitchen_area	21421.0	1.056981e+01	5.905438e+00	1.3	7.00	9.10	12.0	112.0
balcony	12180.0	1.150082e+00	1.071300e+00	0.0	0.00	1.00	2.0	5.0
airports_nearest	18157.0	2.879367e+04	1.263088e+04	0.0	18585.00	26726.00	37273.0	84869.0
cityCenters_nearest	18180.0	1.419128e+04	8.608386e+03	181.0	9238.00	13098.50	16293.0	65968.0
parks_around3000	18181.0	6.114075e-01	8.020736e-01	0.0	0.00	0.00	1.0	3.0
parks_nearest	8079.0	4.908046e+02	3.423180e+02	1.0	288.00	455.00	612.0	3190.0
ponds_around3000	18181.0	7.702547e-01	9.383456e-01	0.0	0.00	1.00	1.0	3.0
ponds_nearest	9110.0	5.179809e+02	2.777206e+02	13.0	294.00	502.00	729.0	1344.0
days_exposition	20518.0	1.808886e+02	2.197280e+02	1.0	45.00	95.00	232.0	1580.0

	locality_name
Санкт-петербург	15721
Мурино	590
Кудрово	472
Шушары	440
Всеволожск	398
Пельгора	1
Каложицы	1
Платформа 69-й километр	1
Почап	1
Дзержинского	1

	count	mean	std	min	25%	50%	75%	max
airports_nearest	23650.0	23512.449852	16667.539974	-1.0	11942.00	23140.0	35841.0	84869.0
cityCenters_nearest	23650.0	11511.521268	9633.272673	-1.0	3870.25	11753.0	15743.0	65968.0
parks_nearest	23650.0	1210.685666	1300.745383	-1.0	-1.00	460.0	3000.0	3190.0
ponds_nearest	23650.0	1425.453362	1330.468317	-1.0	503.00	503.0	3000.0	3000.0

	count	mean	std	min	25%	50%	75%	max	low_std	low_iqr	up_iqr	up_std
kitchen_area	23650.0	10.465152	5.631919	1.3	7.2	9.6	11.4575	112.0	-6.430605	0.81375	17.84375	27.360910
living_area	23650.0	34.054007	21.226308	2.0	19.0	30.4	41.1000	409.7	-29.624918	-14.15000	74.25000	97.732932
total_area	23650.0	60.329069	35.661808	12.0	40.0	52.0	69.7000	900.0	-46.656355	-4.55000	114.25000	167.314493

4. Исследовательский анализ данных ¶

Исследование объявлений о продаже квартир¶

1. Изучение входной информации¶

Описание данных

[Описание данных после предобработки и добавления данных](#describe_data_after_preproc)¶

Изучение общей информации о предоставляемых данных ¶

Вывод¶

Определение и заполнение пропущенных значений ¶

Вывод¶

Изменение типов данных и наименований столбцов ¶

Изучение первичных параметров, удаление редких и выбивающихся значений.¶

Площадь недвижимости¶

Цена недвижимости¶

Количество комнат¶

Высота потолков¶

3. Добавление данных в таблицу¶

Цена квадратного метра ¶

День недели, месяц и год публикации объявления ¶

Этаж квартиры ¶

Соотношение жилой и общей площади и отношение площади кухни к общей ¶

Вывод¶

Описание данных после предобработки и добавления данных

Изучение времени продажи квартиры.¶

Какие факторы больше всего влияют на стоимость квартиры?¶

Вывод¶

Вывод¶

Изучение предложений квартир ¶

Выделиние сегмента квартир в центре и его анализ.¶

Вывод¶

Вывод¶

	count	mean	std	min	25%	50%	75%	max	low_std	low_iqr	up_iqr	up_std
kitchen_total	19024.0	0.191825	0.070288	0.044	0.138	0.179	0.237	0.825	-0.019040	-0.0105	0.3855	0.402691
living_total	19024.0	0.570148	0.118752	0.070	0.495	0.567	0.640	2.408	0.213893	0.2775	0.8575	0.926404

	location	count	price_sq_m
0	Санкт-петербург	10303	103944
1	Мурино	458	85616
2	Шушары	378	77880
3	Кудрово	343	95485
4	Всеволожск	319	66775
5	Колпино	285	75232
6	Парголово	267	90432
7	Пушкин	260	99324
8	Гатчина	244	68386
9	Выборг	174	57208

	location	count	price_sq_m
0	Лисий нос	2	113728
1	Санкт-петербург	10303	103944
2	Сестрорецк	113	102439
3	Зеленогорск	20	100123
4	Пушкин	260	99324
5	Мистолово	8	97145
6	Левашово	1	96997
7	Кудрово	343	95485
8	Парголово	267	90432
9	Стрельна	35	88627

	location	count	price_sq_m
0	Житково	1	14264
1	Ефимовский	2	14149
2	Ям-тесово	2	13711
3	Сижно	1	13709
4	Тeсово-4	1	12931
5	Совхозный	2	12629
6	Выскатка	2	12335
7	Вахнова кара	1	11688
8	Свирь	2	11481
9	Старополье	3	11206

	city_nearest_km
count	16595.000000
mean	71.118530
std	101.371557
min	0.000000
25%	12.000000
50%	15.000000
75%	35.000000
max	255.000000
low_std	-232.996142
low_iqr	-22.500000
up_iqr	69.500000
up_std	375.233201

	count	mean	std	min	25%	50%	75%	max
total_area	1104.0	58.546685	18.641605	17.0	43.975000	56.900000	71.00000	114.200000
price_m	1104.0	6.206522	1.928672	1.0	5.000000	6.000000	8.00000	10.000000
rooms	1104.0	2.092391	0.889434	0.0	1.000000	2.000000	3.00000	5.000000
ceiling_height	1104.0	2.000000	0.000000	2.0	2.000000	2.000000	2.00000	2.000000
price_sq_m	1104.0	118871.933953	28670.807152	26250.0	98585.239033	114557.844492	136043.48238	262711.864407
city_nearest_km	1104.0	4.681159	1.696823	0.0	4.000000	5.000000	6.00000	7.000000
day_exp	1104.0	15.083333	8.600446	1.0	8.000000	15.000000	23.00000	31.000000
month_exp	1104.0	6.664855	3.399109	1.0	4.000000	7.000000	10.00000	12.000000
year_exp	1104.0	2017.352355	0.892161	2015.0	2017.000000	2017.000000	2018.00000	2019.000000